{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":2,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":2,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12","author_layer_release":"2026-06-26"},"query_hash":"b69c47265e35","filters":{"venue":"Journal of the Digital Humanities Association of Southern Africa"}},"results":[{"id":"W7125517337","doi":"10.55492/v6i02.6736","title":"Mafoko: Structuring and Building Open Multilingual Terminologies for South African NLP","year":2025,"lang":"","type":"article","venue":"Journal of the Digital Humanities Association of Southern Africa","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"University of Pretoria; International Development Research Centre; Nvidia","keywords":"Terminology; Interoperability; Bridging (networking); Consistency (knowledge bases); Structuring; Scalability; Machine translation","authors":[{"name":"Vukosi Marivate","is_ca":false},{"name":"Isheanesu Joseph Dzingirai","is_ca":false},{"name":"Fiskani Ella Banda","is_ca":false},{"name":"Richard Lastrucci","is_ca":false},{"name":"Thapelo Sindane","is_ca":false},{"name":"Keabetswe Madumo","is_ca":false},{"name":"Kayode Olaleye","is_ca":false},{"name":"Abiodun Modupe","is_ca":false},{"name":"Unarine Netshifhefhe","is_ca":false},{"name":"Herkulaas Combrink","is_ca":false},{"name":"Mohlatlego Nakeng","is_ca":false},{"name":"Matome Ledwaba","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02697340096356203,"gpt":0.2787776361997294,"spread":0.2518042352361674,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005061758,0.001156553,0.0007296744,0.00669365,0.002470502,0.003444324,0.002122248,0.001518371,0.01048695],"category_scores_gemma":[0.02450108,0.0007536996,0.001679066,0.004379577,0.001545197,0.00756113,0.009805645,0.002870681,0.008413125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001976848,"about_ca_system_score_gemma":0.005309802,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008651732,"about_ca_topic_score_gemma":0.01400715,"domain_scores_codex":[0.9965844,0.001312504,0.0005175198,0.0007164169,0.000646368,0.0002227421],"domain_scores_gemma":[0.9935399,0.002570625,0.000447346,0.002177174,0.0009631714,0.0003019059],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007541061,0.0004178972,0.01175041,0.006438436,0.0002960799,0.002029785,0.0113842,0.01675734,0.03880847,0.1022708,0.4389578,0.3701347],"study_design_scores_gemma":[0.0002945795,0.0001268706,0.007259238,0.001089791,0.00008788932,0.0009806011,0.004633814,0.06030294,0.02036165,0.08003578,0.8246413,0.0001855657],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08334444,0.003067711,0.4747057,0.004804058,0.0009952382,0.003533954,0.3163069,0.07600853,0.03723339],"genre_scores_gemma":[0.0865445,0.0008288653,0.4794304,0.0005744016,0.00009030994,0.002803196,0.4203306,0.005701863,0.003695985],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01048695,"threshold_uncertainty_score":0.0350824,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W7125393895","doi":"10.55492/v6i02.6747","title":"Building Corpora for Low-Resource Kenyan Languages","year":2025,"lang":"","type":"article","venue":"Journal of the Digital Humanities Association of Southern Africa","topic":"ICT in Developing Communities","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Bundesministerium für Wirtschaftliche Zusammenarbeit und Entwicklung; International Development Research Centre; Rockefeller Foundation","keywords":"Languages of Africa; Kenya; Reading (process); Natural language; Corpus linguistics; Text corpus; Computational linguistics; Language identification","authors":[{"name":"Audrey Mbogho","is_ca":false},{"name":"Quin Elizabeth Awuor","is_ca":false},{"name":"Andrew Kipkebut","is_ca":false},{"name":"Lilian Wanzare","is_ca":false},{"name":"Vivian Anyango Oloo","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01795061024483665,"gpt":0.2419945099350392,"spread":0.2240438996902026,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003625405,0.0009596851,0.0005317113,0.005786476,0.004455931,0.002065776,0.001567928,0.00105868,0.0196273],"category_scores_gemma":[0.0127365,0.0008460557,0.0004940002,0.004813637,0.001656361,0.003694072,0.004008006,0.001700345,0.006628809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001555594,"about_ca_system_score_gemma":0.004532571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01001628,"about_ca_topic_score_gemma":0.0340993,"domain_scores_codex":[0.9971448,0.0009536391,0.0004426252,0.0008103098,0.0004551141,0.0001934618],"domain_scores_gemma":[0.9894803,0.004837859,0.0007798168,0.001650369,0.002877503,0.0003741502],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008519169,0.00102186,0.0342701,0.007604052,0.0001581585,0.008594005,0.06909232,0.006941353,0.1379935,0.03553781,0.1788626,0.5190724],"study_design_scores_gemma":[0.0002379856,0.0002579626,0.06789405,0.001496313,0.0001311762,0.002364729,0.02937281,0.00756592,0.03349601,0.00666182,0.8502635,0.0002577617],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5200146,0.003961746,0.1315182,0.003608245,0.001501572,0.01549221,0.2113311,0.004155168,0.1084171],"genre_scores_gemma":[0.3287014,0.001974442,0.3438828,0.0007463876,0.0002687205,0.01925889,0.2838762,0.001752363,0.01953873],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0196273,"threshold_uncertainty_score":0.06565988,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}